`gaitmap.data_transform`.TrainableAbsMaxScaler#

class gaitmap.data_transform.TrainableAbsMaxScaler(out_max: float = 1, data_max: float | None = None)[source]#

Scale data by the absolut max of a trainings sequence.

Warning

By default, this scaler will not modify the data! Use self_optimize to adapt the data_max parameter based on a set of training data.

During training the scaler will calculate the absolute max from the trainings data, Per provided dataset data_max will be calculated. The final data_max is the max over all train sequences.

data_max = max(abs(x_train))

Note that the maximum over all columns is calculated. I.e. Only a single global scaling factor is applied to all the data.

During transformation, this fixed scaling factor is applied to any new columns.

y = x * out_max / data_max

If data_max is 0 (e.g. all-zero training data), the input is returned unchanged.

Parameters:

out_max: The value the maximum will be scaled to. After scaling the absolute maximum in the data will be equal to this value. Note that if the absolute maximum corresponds to a minimum in the data, this minimum will be scaled to -feature_max.
data_max: The maximum of the training data. The value can either be set manually or automatically calculated from the training data using self_optimize.

Other Parameters:

data: The data passed to the transform method.

Attributes:

transformed_data_: The transformed data.

Methods

`clone`()	Create a new instance of the class with all parameters copied over.
`from_json`(json_str)	Import an gaitmap object from its json representation.
`get_params`([deep])	Get parameters for this algorithm.
`self_optimize`(data, **_)	Calculate scaling parameters based on a trainings sequence.
`set_params`(**params)	Set the parameters of this Algorithm.
`to_json`()	Export the current object parameters as json.
`transform`(data, **_)	Scale the data.

__init__(out_max: float = 1, data_max: float | None = None) → None[source]#

clone() → Self[source]#

Create a new instance of the class with all parameters copied over.

This will create a new instance of the class itself and all nested objects

classmethod from_json(json_str: str) → Self[source]#

Import an gaitmap object from its json representation.

For details have a look at the this example.

You can use the to_json method of a class to export it as a compatible json string.

Parameters:

json_str: json formatted string

get_params(deep: bool = True) → dict[str, Any][source]#

Get parameters for this algorithm.

Parameters:

deep: Only relevant if object contains nested algorithm objects. If this is the case and deep is True, the params of these nested objects are included in the output using a prefix like nested_object_name__ (Note the two “_” at the end)

Returns: